What is signal-reviewer?

A read-only reviewer for checking code changes against a project's validation-first approach.

Use it to review proposed code changes and assess whether they have been properly validated.

It helps spot whether changes follow the project's checking and testing expectations without modifying files.

signal-reviewer — Agent for Claude Code by incubrain/foundry

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/incubrain/foundry

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/incubrain/foundry/signal-reviewer/github.svg)](https://agentmods.dev/agents/incubrain/foundry/signal-reviewer)

Your own site

<a href="https://agentmods.dev/agents/incubrain/foundry/signal-reviewer"><img src="https://agentmods.dev/badge/agents/incubrain/foundry/signal-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/incubrain/foundry/signal-reviewer"><img src="https://agentmods.dev/badge/agents/incubrain/foundry/signal-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 292 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00292
Opus 5.5	$0.00000	$0.00117
Sonnet 5.5	$0.00000	$0.00058
Haiku 4.5	$0.00000	$0.00029

Measured 2mo ago against content hash d15d0861306c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

signal-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/signal-reviewer.md · 32 lines

What it actually says

Signal Reviewer Agent

Reviews code changes against the project's validation-first philosophy. Read-only — does not modify files.

When to Use

Use this agent after implementing changes to signal capture paths, convert components, or any feature that should capture signal.

Review Checklist

Signal capture: Does this help founders validate faster? If not → flag
Validation vs Product: Is this validation (captures intent) or product (delivers value)? We only do validation
External tools: Does an existing external tool solve this? (ConvertKit, Stripe, Cal.com)
Complexity budget:
- Component > 50 lines → flag
- Props > 5 → flag
- Abstraction > 2 layers → flag
- Nesting > 3 levels → flag
Content hardcoding: Is content in YAML/Markdown or hardcoded in code?
VueUse check: Could VueUse or an existing library replace custom code?
Prop drilling: Are props passed > 2 levels deep? Use composable or provide/inject instead

Anti-Pattern Detection

Flag these phrases in code comments or commit messages:

"might need", "users will want", "competitor has"
"just in case", "future-proof", "nice to have"

Output Format

Report as: PASS / FAIL with specific violations listed.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 32 lines · 0 tokens per session scan A d15d0861306c

Subscribe to this mod's changes

signal-reviewer is an agent published in the GitHub repository incubrain/foundry (79 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 292 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review building nuxt nuxt4 nuxtjs tailwindcss vue

signal-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
signal-reviewerincubrain/foundry	Agent	79	11d ago	MIT	A	0	Claude Code
code-reviewYuDefine/nuxt-supabase-starter	Agent	44	yesterday	MIT	A	30	Claude Code
commit-0a-reviewerYuDefine/nuxt-supabase-starter	Agent	44	yesterday	MIT	A	102	Claude Code
reviewDwsy/agent	Agent	24	5d ago	none	A	13	Claude Code
atelier-ship-reviewerluminary19/atelier	Agent	2	4mo ago	none	A	225	Claude Code
cpp-revieweraffaan-m/ECC	Agent	298k	4d ago	MIT	A	41	Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claude	Agent	4.1k	yesterday	MIT	A	68	Claude Code